CS 2750: Machine LearningIntroductionProf. Adriana KovashkaUniversity of PittsburghJanuary 6, 2016Course Info• Website: http://people.cs.pitt.edu/~kovashka/cs2750• Instructor: Adriana Kovashka ([email protected]) Use "CS2750" at the beginning of your Subject • Office: Sennott Square 5325 • Office hours: Mon/Wed, 12:15pm-1:15pm• Textbook: Christopher M. Bishop. Pattern Recognition and Machine Learning. Springer, 2006 And other readingsTA• Changsheng Liu• Office: Sennott Square 6805 • Office hours: TBD– Wednesday 1PM to 3PM– Wednesday 4PM to 6PM – Any time Thursday– Do the Doodle by the end of Friday: http://doodle.com/poll/7qinfkgu2xwqrxnaSchedule http://people.cs.pitt.edu/~kovashka/cs2750Grading• Homework (40%)• Project (20%)– Status presentation and report (5%)– Final presentation and report (15%)• Midterm exam (15%)• Final exam (20%)• Participation (5%)Homework• Four homework assignments• Will use Matlab (tutorial next class)• Bias towards computer vision applications• Submission through CourseWeb  CS2750 Assignments  Homework 1, etc.• Attach a zip file with your written responses and code, named YourFirstName_YourLastName.zip • Homework is due at 11:59pm on the due• Grades will appear on CourseWebHomework Late Policy• You get 3 "free" late days, i.e., you can submit homework a total of 3 days late. • For example, you can submit one problem set 12 hours late, and another 60 hours late. • Once you've used up your free late days, you will incur a penalty of 25% from the total project credit possible for each late day. • A late day is anything from 1 minute to 24 hours.Project• Encouraged to work in groups of two• Proposal due Feb. 29• Status report and in-class status presentations March 28• Final report and presentations in last week of class• Aim for workshop-level work• See course website for resources and more infoExams• One mid-term and one final exam• The final exam will be cumulative but will focus on the latter half of the courseReadings• Posted on course website (tentatively)• Subject to change until 6pm on the day of the previous classParticipation• 5% of grade will be based on participation• No attendance will be taken, but if you don’t attend, you can’t participate• How to participate: – Answer questions asked by instructor and others– Ask meaningful questions– Bring in relevant articles about recent developments in machine learning– Contribute on Piazza• Feedback is welcome!Collaboration Policy• You will work individually. The work you turn in must be your own work. • You can discuss the problem sets with your classmates, but do not look at their code. • You cannot use posted solutions, search for code on the internet or use or look at Matlab implementations of something you are asked to write. • When in doubt, ask the instructor or TA! • Plagiarism will cause you to fail the class and receive disciplinary penalty.Disabilities• If you have a disability for which you are or may be requesting an accommodation, you are encouraged to contact both your instructor and Disability Resources and Services (DRS), 140 William Pitt Union, (412) 648-7890, [email protected], (412) 228-5347 for P3 ASL users, as early as possible in the term. DRS will verify your disability and determine reasonable accommodations for this course.Medical Conditions• If you have a medical condition which will prevent you from doing a certain assignment or coming to class, you must inform the instructor of this beforethe deadline. • You must then submit documentation of your condition within a week of the assignment deadline.Prerequisites• Linear algebra• Probability• Calculus • Programming and complexity analysisShould I take this class?• It will be a lot of work!– But you will learn a lot• Some parts will be hard and require that you pay close attention!– But I will have periodic ungraded pop quizzes to see how you’re doing– I will also pick on students randomly to answer questions– Use instructor’s and TA’s office hours!!!Questions?Plan for Today• Course structure and policies• Introductions• What is machine learning?– Example problems– Framework – ChallengesIntroductions• What is your name?• What is your department and year in the program?• What are your research interests?• What one thing outside of school are you passionate about?• What do you hope to get out of this class?What is machine learning?• Finding patterns and relationships in data• We can apply these patterns to make useful predictions • E.g. we can predict how much a user will like a movie, even though that user never rated that movieExample machine learning tasks• Netflix challenge– Given lots of data about how users rated movies (training data)– But we don’t know how user i will rate movie j and want to predict that (test data)Example machine learning tasks• Spam or not?vsSlide credit: Dhruv BatraExample machine learning tasks• Weather predictionTemperatureSlide credit: Carlos GuestrinExample machine learning tasks• Who will win <contest of your choice>?Example machine learning tasks• Machine translationSlide credit: Dhruv Batra, figure credit: Kevin GimpelExample machine learning tasks• Speech recognitionSlide credit: Carlos GuestrinExample machine learning tasks• Pose estimationSlide credit: Noah SnavelyExample machine learning tasks• Face recognition Slide credit: Noah SnavelyExample machine learning tasks• Image categorizationPizzaWineStoveSlide credit: Dhruv BatraExample machine learning tasksIs it alive?Is it dangerous?How fast does it run?Is it soft?Does it have a tail?Can I poke with it?Slide credit: Derek HoiemExample machine learning tasks• Attribute-based image retrievalKovashka et al., “WhittleSearch: Image Search with Relative Attribute Feedback”, CVPR 2012Example machine learning tasks• Dating car photographsLee et al., “Style-aware Mid-level Representation for Discovering Visual Connections in Space and Time”, ICCV 2013Example machine learning tasks• Inferring visual persuasionJoo et al., “Visual Persuasion: Inferring Communicative Intents of Images”, CVPR 2014Example machine learning tasks• Answering questions about imagesAntol et al., “VQA: Visual Question Answering”, ICCV 2015Example machine learning tasks• What else?Plan for Today• Course structure and policies•